A topology-preserving dimensionality reduction method for single-cell RNA-seq data using graph autoencoder

Abstract Dimensionality reduction is crucial for the visualization and interpretation of the high-dimensional single-cell RNA sequencing (scRNA-seq) data. However, preserving topological structure among cells to low dimensional space remains a challenge. Here, we present the single-cell graph autoen...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Zixiang Luo, Chenyu Xu, Zhen Zhang, Wenfei Jin
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/30dec251c0cd4590a65a1c8076f91bcf
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:30dec251c0cd4590a65a1c8076f91bcf
record_format dspace
spelling oai:doaj.org-article:30dec251c0cd4590a65a1c8076f91bcf2021-12-02T18:01:40ZA topology-preserving dimensionality reduction method for single-cell RNA-seq data using graph autoencoder10.1038/s41598-021-99003-72045-2322https://doaj.org/article/30dec251c0cd4590a65a1c8076f91bcf2021-10-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-99003-7https://doaj.org/toc/2045-2322Abstract Dimensionality reduction is crucial for the visualization and interpretation of the high-dimensional single-cell RNA sequencing (scRNA-seq) data. However, preserving topological structure among cells to low dimensional space remains a challenge. Here, we present the single-cell graph autoencoder (scGAE), a dimensionality reduction method that preserves topological structure in scRNA-seq data. scGAE builds a cell graph and uses a multitask-oriented graph autoencoder to preserve topological structure information and feature information in scRNA-seq data simultaneously. We further extended scGAE for scRNA-seq data visualization, clustering, and trajectory inference. Analyses of simulated data showed that scGAE accurately reconstructs developmental trajectory and separates discrete cell clusters under different scenarios, outperforming recently developed deep learning methods. Furthermore, implementation of scGAE on empirical data showed scGAE provided novel insights into cell developmental lineages and preserved inter-cluster distances.Zixiang LuoChenyu XuZhen ZhangWenfei JinNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-8 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Zixiang Luo
Chenyu Xu
Zhen Zhang
Wenfei Jin
A topology-preserving dimensionality reduction method for single-cell RNA-seq data using graph autoencoder
description Abstract Dimensionality reduction is crucial for the visualization and interpretation of the high-dimensional single-cell RNA sequencing (scRNA-seq) data. However, preserving topological structure among cells to low dimensional space remains a challenge. Here, we present the single-cell graph autoencoder (scGAE), a dimensionality reduction method that preserves topological structure in scRNA-seq data. scGAE builds a cell graph and uses a multitask-oriented graph autoencoder to preserve topological structure information and feature information in scRNA-seq data simultaneously. We further extended scGAE for scRNA-seq data visualization, clustering, and trajectory inference. Analyses of simulated data showed that scGAE accurately reconstructs developmental trajectory and separates discrete cell clusters under different scenarios, outperforming recently developed deep learning methods. Furthermore, implementation of scGAE on empirical data showed scGAE provided novel insights into cell developmental lineages and preserved inter-cluster distances.
format article
author Zixiang Luo
Chenyu Xu
Zhen Zhang
Wenfei Jin
author_facet Zixiang Luo
Chenyu Xu
Zhen Zhang
Wenfei Jin
author_sort Zixiang Luo
title A topology-preserving dimensionality reduction method for single-cell RNA-seq data using graph autoencoder
title_short A topology-preserving dimensionality reduction method for single-cell RNA-seq data using graph autoencoder
title_full A topology-preserving dimensionality reduction method for single-cell RNA-seq data using graph autoencoder
title_fullStr A topology-preserving dimensionality reduction method for single-cell RNA-seq data using graph autoencoder
title_full_unstemmed A topology-preserving dimensionality reduction method for single-cell RNA-seq data using graph autoencoder
title_sort topology-preserving dimensionality reduction method for single-cell rna-seq data using graph autoencoder
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/30dec251c0cd4590a65a1c8076f91bcf
work_keys_str_mv AT zixiangluo atopologypreservingdimensionalityreductionmethodforsinglecellrnaseqdatausinggraphautoencoder
AT chenyuxu atopologypreservingdimensionalityreductionmethodforsinglecellrnaseqdatausinggraphautoencoder
AT zhenzhang atopologypreservingdimensionalityreductionmethodforsinglecellrnaseqdatausinggraphautoencoder
AT wenfeijin atopologypreservingdimensionalityreductionmethodforsinglecellrnaseqdatausinggraphautoencoder
AT zixiangluo topologypreservingdimensionalityreductionmethodforsinglecellrnaseqdatausinggraphautoencoder
AT chenyuxu topologypreservingdimensionalityreductionmethodforsinglecellrnaseqdatausinggraphautoencoder
AT zhenzhang topologypreservingdimensionalityreductionmethodforsinglecellrnaseqdatausinggraphautoencoder
AT wenfeijin topologypreservingdimensionalityreductionmethodforsinglecellrnaseqdatausinggraphautoencoder
_version_ 1718378978349154304